Martin, Andreas
Lade...
E-Mail-Adresse
Geburtsdatum
Projekt
Organisationseinheiten
Berufsbeschreibung
Nachname
Martin
Vorname
Andreas
Name
Martin, Andreas
4 Ergebnisse
Suchergebnisse
Gerade angezeigt 1 - 4 von 4
- PublikationLearning and engineering similarity functions for business recommenders(2019) Witschel, Hans Friedrich; Martin, Andreas; Martin, Andreas; Hinkelmann, Knut; Gerber, Aurona; Lenat, Doug; Harmelen, Frank van; Clark, Peter [in: Proceedings of the AAAI 2019 Spring Symposium on Combining Machine Learning with Knowledge Engineering (AAAI-MAKE 2019)]We study the optimisation of similarity measures in tasks where the computation of similarities is not directly visible to end users, namely clustering and case-based recommenders. In both, similarity plays a crucial role, but there are also other algorithmic components that contribute to the end result. Our suggested approach introduces a new form of interaction into these scenarios that make the use of similarities transparent to end users and thus allows to gather direct feedback about similarity from them. This happens without distracting them from their goal – rather allowing them to obtain better and more trustworthy results by excluding dissimilar items. We then propose to use the feedback in a way that incorporates machine learning for updating weights and decisions of knowledge engineers about possible additional features, based on insights derived from a summary of user feedback. The reviewed literature and our own previous empirical investigations suggest that this is the most feasible way – involving both machine and human, each in a task that they are particularly good at.04B - Beitrag Konferenzschrift
- PublikationTraining and re-using human experience: a recommender for more accurate cost estimates in project planning(SciTePress, 2018) Rudolf von Rohr, Christian; Witschel, Hans Friedrich; Martin, Andreas [in: IC3K 2018 - Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management]In many industries, companies deliver customised solutions to their (business) customers within projects. Estimating the human effort involved in such projects is a difficult task and underestimating efforts can lead to non-billable hours, i.e. financial loss on the side of the solution provider. Previous work in this area has focused on automatic estimation of the cost of software projects and has largely ignored the interaction between automated estimation support and human project leads. Our main hypothesis is that an adequate design of such interaction will increase the acceptance of automatically derived estimates and that it will allow for a fruitful combination of data-driven insights and human experience. We therefore build a recommender that is applicable beyond software projects and that suggests job positions to be added to projects and estimated effort of such positions. The recommender is based on the analysis of similar cases (case-based reasoning), "explains" derived similarities and allows human intervention to manually adjust the outcomes. Our experiments show that recommendations were considered helpful and that the ability of the system to explain and adjust these recommendations was heavily used and increased the trust in the system. We conjecture that the interaction of project leads with the system will help to further improve the accuracy of recommendations and the support of human learning in the future.04B - Beitrag Konferenzschrift
- PublikationRandom walks on human knowledge: incorporating human knowledge into data-driven recommenders(2018) Witschel, Hans Friedrich; Martin, Andreas; Bernardino, Jorge; Salgado, Ana; Filipe, Joaquim [in: IC3K 2018. 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management. Proceedings]We explore the use of recommender systems in business scenarios such as consultancy. In these situations, apart from personal preferences of users, knowledge about objective business-driven criteria plays a role. We investigate strategies for representing and incorporating such knowledge into data-driven recommenders. As a baseline, we choose a robust and flexible paradigm that is based on a simple graph-based representation of past customer cases and choices, in combination with biased random walks. On a real data set from a business intelligence consultancy firm, we study how the incorporation of two important types of explicit human knowledge – namely taxonomic and associative knowledge – impacts the effectiveness of a data-driven recommender. Our results show no consistent improvement for taxonomic knowledge, but quite substantial and significant gains when using associative knowledge.04B - Beitrag Konferenzschrift
- PublikationRefining process models through the analysis of informal work practice(2011) Brander, Simon; Hinkelmann, Knut; Hu, Bo; Martin, Andreas; Riss, Uwe; Thönssen, Barbara; Witschel, Hans FriedrichThe work presented in this paper explores the potential of leveraging the traces of informal work and collaboration in order to improve business processes over time. As process executions often differ from the original design due to individual preferences, skills or competencies and exceptions, we propose methods to analyse personal preferences of work, such as email communication and personal task execution in a task management application. Outcome of these methods is the detection of internal substructures (subtasks or branches) of activities on the one hand and the recommendation of resources to be used in activities on the other hand, leading to the improvement of business process models. Our first results show that even though human intervention is still required to operationalise these insights it is indeed possible to derive interesting and new insights about business processes from traces of informal work and infer suggestions for process model changes.04B - Beitrag Konferenzschrift